Learning adaptive temporal radio maps for signal-strength-based location estimation
Learning adaptive temporal radio maps for signal-strength-based location estimation
复制标题
学习自适应时间无线电地图以进行基于信号强度的位置估计
DOI：
10.1109/tmc.2007.70764
复制
发表时间：
2008-07-01
影响因子：
7.9
通讯作者：
Ni, Lionel M.
中科院分区：
文献类型：
--
作者：
Yin, Jie;Yang, Qiang;Ni, Lionel M.
在无线网络中，可以使用从信号发射器接收的信号强度来估计客户端的位置。基于静态指纹的技术通常用于位置估计，其中通过在离线阶段校准信号强度值来构建无线电地图。这些值被编译成确定性或概率性模型，用于在线本地化。然而，当信号强度值由于环境动态而随时间变化时，无线电地图可能会过时，并且重复的数据校准是不可行的或昂贵的。在本文中，我们提出了一种新的算法，被称为位置估计使用模型树（LEMT），通过使用在参考点接收到的实时信号强度读数来重建无线电地图。该算法可以考虑每个时间点的实时信号强度值，并利用估计位置与参考点之间的相关性。我们表明，这种技术可以有效地适应在不同的时间段内的信号强度的变化，而不需要重复重建的无线电地图。LEMT的有效性证明使用两个真实的数据集收集的802.11 b无线网络和射频识别（RFID）为基础的网络。
In wireless networks, a client's locations can be estimated using signal strength received from signal transmitters. Static fingerprint-based techniques are commonly used for location estimation, in which a radio map is built by calibrating signal-strength values in the offline phase. These values, compiled into deterministic or probabilistic models, are used for online localization. However, the radio map can be outdated when signal-strength values change over time due to environmental dynamics, and repeated data calibration is infeasible or expensive. In this paper, we present a novel algorithm, known as Location Estimation using Model Trees (LEMT), to reconstruct a radio map by using real-time signal-strength readings received at the reference points. This algorithm can take real-time signal-strength values at each time point into account and make use of the dependency between the estimated locations and reference points. We show that this technique can effectively accommodate the variations of signal strength over different time periods without the need to repeatedly rebuild the radio maps. The effectiveness of LEMT is demonstrated using two real data sets collected from an 802.11b wireless network and a Radio Frequency Identification (RFID)-based network.